aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig36
-rw-r--r--kernel/trace/Makefile1
-rw-r--r--kernel/trace/bpf_trace.c222
-rw-r--r--kernel/trace/ftrace.c44
-rw-r--r--kernel/trace/ring_buffer.c10
-rw-r--r--kernel/trace/trace.c491
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_entries.h6
-rw-r--r--kernel/trace/trace_events.c168
-rw-r--r--kernel/trace/trace_export.c2
-rw-r--r--kernel/trace/trace_functions_graph.c15
-rw-r--r--kernel/trace/trace_kprobe.c25
-rw-r--r--kernel/trace/trace_probe.c19
-rw-r--r--kernel/trace/trace_probe.h12
-rw-r--r--kernel/trace/trace_stack.c4
-rw-r--r--kernel/trace/trace_stat.c10
-rw-r--r--kernel/trace/trace_uprobe.c15
17 files changed, 886 insertions, 198 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a5da09c899dd..3b9a48ae153a 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -432,6 +432,14 @@ config UPROBE_EVENT
This option is required if you plan to use perf-probe subcommand
of perf tools on user space applications.
+config BPF_EVENTS
+ depends on BPF_SYSCALL
+ depends on KPROBE_EVENT
+ bool
+ default y
+ help
+ This allows the user to attach BPF programs to kprobe events.
+
config PROBE_EVENTS
def_bool n
@@ -599,6 +607,34 @@ config RING_BUFFER_STARTUP_TEST
If unsure, say N
+config TRACE_ENUM_MAP_FILE
+ bool "Show enum mappings for trace events"
+ depends on TRACING
+ help
+ The "print fmt" of the trace events will show the enum names instead
+ of their values. This can cause problems for user space tools that
+ use this string to parse the raw data as user space does not know
+ how to convert the string to its value.
+
+ To fix this, there's a special macro in the kernel that can be used
+ to convert the enum into its value. If this macro is used, then the
+ print fmt strings will have the enums converted to their values.
+
+ If something does not get converted properly, this option can be
+ used to show what enums the kernel tried to convert.
+
+ This option is for debugging the enum conversions. A file is created
+ in the tracing directory called "enum_map" that will show the enum
+ names matched with their values and what trace event system they
+ belong too.
+
+ Normally, the mapping of the strings to values will be freed after
+ boot up or module load. With this option, they will not be freed, as
+ they are needed for the "enum_map" file. Enabling this option will
+ increase the memory footprint of the running kernel.
+
+ If unsure, say N
+
endif # FTRACE
endif # TRACING_SUPPORT
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 98f26588255e..9b1044e936a6 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -53,6 +53,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM),y)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
new file mode 100644
index 000000000000..2d56ce501632
--- /dev/null
+++ b/kernel/trace/bpf_trace.c
@@ -0,0 +1,222 @@
+/* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/uaccess.h>
+#include <linux/ctype.h>
+#include "trace.h"
+
+static DEFINE_PER_CPU(int, bpf_prog_active);
+
+/**
+ * trace_call_bpf - invoke BPF program
+ * @prog: BPF program
+ * @ctx: opaque context pointer
+ *
+ * kprobe handlers execute BPF programs via this helper.
+ * Can be used from static tracepoints in the future.
+ *
+ * Return: BPF programs always return an integer which is interpreted by
+ * kprobe handler as:
+ * 0 - return from kprobe (event is filtered out)
+ * 1 - store kprobe event into ring buffer
+ * Other values are reserved and currently alias to 1
+ */
+unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx)
+{
+ unsigned int ret;
+
+ if (in_nmi()) /* not supported yet */
+ return 1;
+
+ preempt_disable();
+
+ if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) {
+ /*
+ * since some bpf program is already running on this cpu,
+ * don't call into another bpf program (same or different)
+ * and don't send kprobe event into ring-buffer,
+ * so return zero here
+ */
+ ret = 0;
+ goto out;
+ }
+
+ rcu_read_lock();
+ ret = BPF_PROG_RUN(prog, ctx);
+ rcu_read_unlock();
+
+ out:
+ __this_cpu_dec(bpf_prog_active);
+ preempt_enable();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(trace_call_bpf);
+
+static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ void *dst = (void *) (long) r1;
+ int size = (int) r2;
+ void *unsafe_ptr = (void *) (long) r3;
+
+ return probe_kernel_read(dst, unsafe_ptr, size);
+}
+
+static const struct bpf_func_proto bpf_probe_read_proto = {
+ .func = bpf_probe_read,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_STACK,
+ .arg2_type = ARG_CONST_STACK_SIZE,
+ .arg3_type = ARG_ANYTHING,
+};
+
+static u64 bpf_ktime_get_ns(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ /* NMI safe access to clock monotonic */
+ return ktime_get_mono_fast_ns();
+}
+
+static const struct bpf_func_proto bpf_ktime_get_ns_proto = {
+ .func = bpf_ktime_get_ns,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+};
+
+/*
+ * limited trace_printk()
+ * only %d %u %x %ld %lu %lx %lld %llu %llx %p conversion specifiers allowed
+ */
+static u64 bpf_trace_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
+{
+ char *fmt = (char *) (long) r1;
+ int mod[3] = {};
+ int fmt_cnt = 0;
+ int i;
+
+ /*
+ * bpf_check()->check_func_arg()->check_stack_boundary()
+ * guarantees that fmt points to bpf program stack,
+ * fmt_size bytes of it were initialized and fmt_size > 0
+ */
+ if (fmt[--fmt_size] != 0)
+ return -EINVAL;
+
+ /* check format string for allowed specifiers */
+ for (i = 0; i < fmt_size; i++) {
+ if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i]))
+ return -EINVAL;
+
+ if (fmt[i] != '%')
+ continue;
+
+ if (fmt_cnt >= 3)
+ return -EINVAL;
+
+ /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */
+ i++;
+ if (fmt[i] == 'l') {
+ mod[fmt_cnt]++;
+ i++;
+ } else if (fmt[i] == 'p') {
+ mod[fmt_cnt]++;
+ i++;
+ if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0)
+ return -EINVAL;
+ fmt_cnt++;
+ continue;
+ }
+
+ if (fmt[i] == 'l') {
+ mod[fmt_cnt]++;
+ i++;
+ }
+
+ if (fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x')
+ return -EINVAL;
+ fmt_cnt++;
+ }
+
+ return __trace_printk(1/* fake ip will not be printed */, fmt,
+ mod[0] == 2 ? r3 : mod[0] == 1 ? (long) r3 : (u32) r3,
+ mod[1] == 2 ? r4 : mod[1] == 1 ? (long) r4 : (u32) r4,
+ mod[2] == 2 ? r5 : mod[2] == 1 ? (long) r5 : (u32) r5);
+}
+
+static const struct bpf_func_proto bpf_trace_printk_proto = {
+ .func = bpf_trace_printk,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_STACK,
+ .arg2_type = ARG_CONST_STACK_SIZE,
+};
+
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+{
+ switch (func_id) {
+ case BPF_FUNC_map_lookup_elem:
+ return &bpf_map_lookup_elem_proto;
+ case BPF_FUNC_map_update_elem:
+ return &bpf_map_update_elem_proto;
+ case BPF_FUNC_map_delete_elem:
+ return &bpf_map_delete_elem_proto;
+ case BPF_FUNC_probe_read:
+ return &bpf_probe_read_proto;
+ case BPF_FUNC_ktime_get_ns:
+ return &bpf_ktime_get_ns_proto;
+
+ case BPF_FUNC_trace_printk:
+ /*
+ * this program might be calling bpf_trace_printk,
+ * so allocate per-cpu printk buffers
+ */
+ trace_printk_init_buffers();
+
+ return &bpf_trace_printk_proto;
+ default:
+ return NULL;
+ }
+}
+
+/* bpf+kprobe programs can access fields of 'struct pt_regs' */
+static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ /* check bounds */
+ if (off < 0 || off >= sizeof(struct pt_regs))
+ return false;
+
+ /* only read is allowed */
+ if (type != BPF_READ)
+ return false;
+
+ /* disallow misaligned access */
+ if (off % size != 0)
+ return false;
+
+ return true;
+}
+
+static struct bpf_verifier_ops kprobe_prog_ops = {
+ .get_func_proto = kprobe_prog_func_proto,
+ .is_valid_access = kprobe_prog_is_valid_access,
+};
+
+static struct bpf_prog_type_list kprobe_tl = {
+ .ops = &kprobe_prog_ops,
+ .type = BPF_PROG_TYPE_KPROBE,
+};
+
+static int __init register_kprobe_prog_ops(void)
+{
+ bpf_register_prog_type(&kprobe_tl);
+ return 0;
+}
+late_initcall(register_kprobe_prog_ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4f228024055b..02bece4a99ea 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -18,7 +18,7 @@
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
#include <linux/suspend.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/hardirq.h>
#include <linux/kthread.h>
#include <linux/uaccess.h>
@@ -249,6 +249,19 @@ static void update_function_graph_func(void);
static inline void update_function_graph_func(void) { }
#endif
+
+static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops)
+{
+ /*
+ * If this is a dynamic ops or we force list func,
+ * then it needs to call the list anyway.
+ */
+ if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC)
+ return ftrace_ops_list_func;
+
+ return ftrace_ops_get_func(ops);
+}
+
static void update_ftrace_function(void)
{
ftrace_func_t func;
@@ -270,7 +283,7 @@ static void update_ftrace_function(void)
* then have the mcount trampoline call the function directly.
*/
} else if (ftrace_ops_list->next == &ftrace_list_end) {
- func = ftrace_ops_get_func(ftrace_ops_list);
+ func = ftrace_ops_get_list_func(ftrace_ops_list);
} else {
/* Just use the default ftrace_ops */
@@ -1008,7 +1021,7 @@ static struct tracer_stat function_stats __initdata = {
.stat_show = function_stat_show
};
-static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
{
struct ftrace_profile_stat *stat;
struct dentry *entry;
@@ -1044,15 +1057,15 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
}
}
- entry = debugfs_create_file("function_profile_enabled", 0644,
+ entry = tracefs_create_file("function_profile_enabled", 0644,
d_tracer, NULL, &ftrace_profile_fops);
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'function_profile_enabled' entry\n");
}
#else /* CONFIG_FUNCTION_PROFILER */
-static __init void ftrace_profile_debugfs(struct dentry *d_tracer)
+static __init void ftrace_profile_tracefs(struct dentry *d_tracer)
{
}
#endif /* CONFIG_FUNCTION_PROFILER */
@@ -4712,7 +4725,7 @@ void ftrace_destroy_filter_files(struct ftrace_ops *ops)
mutex_unlock(&ftrace_lock);
}
-static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
+static __init int ftrace_init_dyn_tracefs(struct dentry *d_tracer)
{
trace_create_file("available_filter_functions", 0444,
@@ -5020,7 +5033,7 @@ static int __init ftrace_nodyn_init(void)
}
core_initcall(ftrace_nodyn_init);
-static inline int ftrace_init_dyn_debugfs(struct dentry *d_tracer) { return 0; }
+static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; }
static inline void ftrace_startup_enable(int command) { }
static inline void ftrace_startup_all(int command) { }
/* Keep as macros so we do not need to define the commands */
@@ -5209,13 +5222,6 @@ static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
{
/*
- * If this is a dynamic ops or we force list func,
- * then it needs to call the list anyway.
- */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC)
- return ftrace_ops_list_func;
-
- /*
* If the func handles its own recursion, call it directly.
* Otherwise call the recursion protected function that
* will call the ftrace ops function.
@@ -5473,7 +5479,7 @@ static const struct file_operations ftrace_pid_fops = {
.release = ftrace_pid_release,
};
-static __init int ftrace_init_debugfs(void)
+static __init int ftrace_init_tracefs(void)
{
struct dentry *d_tracer;
@@ -5481,16 +5487,16 @@ static __init int ftrace_init_debugfs(void)
if (IS_ERR(d_tracer))
return 0;
- ftrace_init_dyn_debugfs(d_tracer);
+ ftrace_init_dyn_tracefs(d_tracer);
trace_create_file("set_ftrace_pid", 0644, d_tracer,
NULL, &ftrace_pid_fops);
- ftrace_profile_debugfs(d_tracer);
+ ftrace_profile_tracefs(d_tracer);
return 0;
}
-fs_initcall(ftrace_init_debugfs);
+fs_initcall(ftrace_init_tracefs);
/**
* ftrace_kill - kill ftrace
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5040d44fe5a3..0315d43176d8 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -2679,7 +2679,7 @@ static DEFINE_PER_CPU(unsigned int, current_context);
static __always_inline int trace_recursive_lock(void)
{
- unsigned int val = this_cpu_read(current_context);
+ unsigned int val = __this_cpu_read(current_context);
int bit;
if (in_interrupt()) {
@@ -2696,18 +2696,14 @@ static __always_inline int trace_recursive_lock(void)
return 1;
val |= (1 << bit);
- this_cpu_write(current_context, val);
+ __this_cpu_write(current_context, val);
return 0;
}
static __always_inline void trace_recursive_unlock(void)
{
- unsigned int val = this_cpu_read(current_context);
-
- val--;
- val &= this_cpu_read(current_context);
- this_cpu_write(current_context, val);
+ __this_cpu_and(current_context, __this_cpu_read(current_context) - 1);
}
#else
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d44901bcd867..05330494a0df 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -20,6 +20,7 @@
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/pagemap.h>
#include <linux/hardirq.h>
#include <linux/linkage.h>
@@ -31,6 +32,7 @@
#include <linux/splice.h>
#include <linux/kdebug.h>
#include <linux/string.h>
+#include <linux/mount.h>
#include <linux/rwsem.h>
#include <linux/slab.h>
#include <linux/ctype.h>
@@ -123,6 +125,42 @@ enum ftrace_dump_mode ftrace_dump_on_oops;
/* When set, tracing will stop when a WARN*() is hit */
int __disable_trace_on_warning;
+#ifdef CONFIG_TRACE_ENUM_MAP_FILE
+/* Map of enums to their values, for "enum_map" file */
+struct trace_enum_map_head {
+ struct module *mod;
+ unsigned long length;
+};
+
+union trace_enum_map_item;
+
+struct trace_enum_map_tail {
+ /*
+ * "end" is first and points to NULL as it must be different
+ * than "mod" or "enum_string"
+ */
+ union trace_enum_map_item *next;
+ const char *end; /* points to NULL */
+};
+
+static DEFINE_MUTEX(trace_enum_mutex);
+
+/*
+ * The trace_enum_maps are saved in an array with two extra elements,
+ * one at the beginning, and one at the end. The beginning item contains
+ * the count of the saved maps (head.length), and the module they
+ * belong to if not built in (head.mod). The ending item contains a
+ * pointer to the next array of saved enum_map items.
+ */
+union trace_enum_map_item {
+ struct trace_enum_map map;
+ struct trace_enum_map_head head;
+ struct trace_enum_map_tail tail;
+};
+
+static union trace_enum_map_item *trace_enum_maps;
+#endif /* CONFIG_TRACE_ENUM_MAP_FILE */
+
static int tracing_set_tracer(struct trace_array *tr, const char *buf);
#define MAX_TRACER_SIZE 100
@@ -3908,6 +3946,182 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = {
.write = tracing_saved_cmdlines_size_write,
};
+#ifdef CONFIG_TRACE_ENUM_MAP_FILE
+static union trace_enum_map_item *
+update_enum_map(union trace_enum_map_item *ptr)
+{
+ if (!ptr->map.enum_string) {
+ if (ptr->tail.next) {
+ ptr = ptr->tail.next;
+ /* Set ptr to the next real item (skip head) */
+ ptr++;
+ } else
+ return NULL;
+ }
+ return ptr;
+}
+
+static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos)
+{
+ union trace_enum_map_item *ptr = v;
+
+ /*
+ * Paranoid! If ptr points to end, we don't want to increment past it.
+ * This really should never happen.
+ */
+ ptr = update_enum_map(ptr);
+ if (WARN_ON_ONCE(!ptr))
+ return NULL;
+
+ ptr++;
+
+ (*pos)++;
+
+ ptr = update_enum_map(ptr);
+
+ return ptr;
+}
+
+static void *enum_map_start(struct seq_file *m, loff_t *pos)
+{
+ union trace_enum_map_item *v;
+ loff_t l = 0;
+
+ mutex_lock(&trace_enum_mutex);
+
+ v = trace_enum_maps;
+ if (v)
+ v++;
+
+ while (v && l < *pos) {
+ v = enum_map_next(m, v, &l);
+ }
+
+ return v;
+}
+
+static void enum_map_stop(struct seq_file *m, void *v)
+{
+ mutex_unlock(&trace_enum_mutex);
+}
+
+static int enum_map_show(struct seq_file *m, void *v)
+{
+ union trace_enum_map_item *ptr = v;
+
+ seq_printf(m, "%s %ld (%s)\n",
+ ptr->map.enum_string, ptr->map.enum_value,
+ ptr->map.system);
+
+ return 0;
+}
+
+static const struct seq_operations tracing_enum_map_seq_ops = {
+ .start = enum_map_start,
+ .next = enum_map_next,
+ .stop = enum_map_stop,
+ .show = enum_map_show,
+};
+
+static int tracing_enum_map_open(struct inode *inode, struct file *filp)
+{
+ if (tracing_disabled)
+ return -ENODEV;
+
+ return seq_open(filp, &tracing_enum_map_seq_ops);
+}
+
+static const struct file_operations tracing_enum_map_fops = {
+ .open = tracing_enum_map_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static inline union trace_enum_map_item *
+trace_enum_jmp_to_tail(union trace_enum_map_item *ptr)
+{
+ /* Return tail of array given the head */
+ return ptr + ptr->head.length + 1;
+}
+
+static void
+trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start,
+ int len)
+{
+ struct trace_enum_map **stop;
+ struct trace_enum_map **map;
+ union trace_enum_map_item *map_array;
+ union trace_enum_map_item *ptr;
+
+ stop = start + len;
+
+ /*
+ * The trace_enum_maps contains the map plus a head and tail item,
+ * where the head holds the module and length of array, and the
+ * tail holds a pointer to the next list.
+ */
+ map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL);
+ if (!map_array) {
+ pr_warning("Unable to allocate trace enum mapping\n");
+ return;
+ }
+
+ mutex_lock(&trace_enum_mutex);
+
+ if (!trace_enum_maps)
+ trace_enum_maps = map_array;
+ else {
+ ptr = trace_enum_maps;
+ for (;;) {
+ ptr = trace_enum_jmp_to_tail(ptr);
+ if (!ptr->tail.next)
+ break;
+ ptr = ptr->tail.next;
+
+ }
+ ptr->tail.next = map_array;
+ }
+ map_array->head.mod = mod;
+ map_array->head.length = len;
+ map_array++;
+
+ for (map = start; (unsigned long)map < (unsigned long)stop; map++) {
+ map_array->map = **map;
+ map_array++;
+ }
+ memset(map_array, 0, sizeof(*map_array));
+
+ mutex_unlock(&trace_enum_mutex);
+}
+
+static void trace_create_enum_file(struct dentry *d_tracer)
+{
+ trace_create_file("enum_map", 0444, d_tracer,
+ NULL, &tracing_enum_map_fops);
+}
+
+#else /* CONFIG_TRACE_ENUM_MAP_FILE */
+static inline void trace_create_enum_file(struct dentry *d_tracer) { }
+static inline void trace_insert_enum_map_file(struct module *mod,
+ struct trace_enum_map **start, int len) { }
+#endif /* !CONFIG_TRACE_ENUM_MAP_FILE */
+
+static void trace_insert_enum_map(struct module *mod,
+ struct trace_enum_map **start, int len)
+{
+ struct trace_enum_map **map;
+
+ if (len <= 0)
+ return;
+
+ map = start;
+
+ trace_event_enum_update(map, len);
+
+ trace_insert_enum_map_file(mod, start, len);
+}
+
static ssize_t
tracing_set_trace_read(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
@@ -4105,9 +4319,24 @@ static void tracing_set_nop(struct trace_array *tr)
tr->current_trace = &nop_trace;
}
-static int tracing_set_tracer(struct trace_array *tr, const char *buf)
+static void update_tracer_options(struct trace_array *tr, struct tracer *t)
{
static struct trace_option_dentry *topts;
+
+ /* Only enable if the directory has been created already. */
+ if (!tr->dir)
+ return;
+
+ /* Currently, only the top instance has options */
+ if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL))
+ return;
+
+ destroy_trace_option_files(topts);
+ topts = create_trace_option_files(tr, t);
+}
+
+static int tracing_set_tracer(struct trace_array *tr, const char *buf)
+{
struct tracer *t;
#ifdef CONFIG_TRACER_MAX_TRACE
bool had_max_tr;
@@ -4172,11 +4401,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
free_snapshot(tr);
}
#endif
- /* Currently, only the top instance has options */
- if (tr->flags & TRACE_ARRAY_FL_GLOBAL) {
- destroy_trace_option_files(topts);
- topts = create_trace_option_files(tr, t);
- }
+ update_tracer_options(tr, t);
#ifdef CONFIG_TRACER_MAX_TRACE
if (t->use_max_tr && !had_max_tr) {
@@ -5817,6 +6042,14 @@ static inline __init int register_snapshot_cmd(void) { return 0; }
static struct dentry *tracing_get_dentry(struct trace_array *tr)
{
+ if (WARN_ON(!tr->dir))
+ return ERR_PTR(-ENODEV);
+
+ /* Top directory uses NULL as the parent */
+ if (tr->flags & TRACE_ARRAY_FL_GLOBAL)
+ return NULL;
+
+ /* All sub buffers have a descriptor */
return tr->dir;
}
@@ -5831,10 +6064,10 @@ static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu)
if (IS_ERR(d_tracer))
return NULL;
- tr->percpu_dir = debugfs_create_dir("per_cpu", d_tracer);
+ tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer);
WARN_ONCE(!tr->percpu_dir,
- "Could not create debugfs directory 'per_cpu/%d'\n", cpu);
+ "Could not create tracefs directory 'per_cpu/%d'\n", cpu);
return tr->percpu_dir;
}
@@ -5851,7 +6084,7 @@ trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent,
}
static void
-tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
+tracing_init_tracefs_percpu(struct trace_array *tr, long cpu)
{
struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu);
struct dentry *d_cpu;
@@ -5861,9 +6094,9 @@ tracing_init_debugfs_percpu(struct trace_array *tr, long cpu)
return;
snprintf(cpu_dir, 30, "cpu%ld", cpu);
- d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
+ d_cpu = tracefs_create_dir(cpu_dir, d_percpu);
if (!d_cpu) {
- pr_warning("Could not create debugfs '%s' entry\n", cpu_dir);
+ pr_warning("Could not create tracefs '%s' entry\n", cpu_dir);
return;
}
@@ -6015,9 +6248,9 @@ struct dentry *trace_create_file(const char *name,
{
struct dentry *ret;
- ret = debugfs_create_file(name, mode, parent, data, fops);
+ ret = tracefs_create_file(name, mode, parent, data, fops);
if (!ret)
- pr_warning("Could not create debugfs '%s' entry\n", name);
+ pr_warning("Could not create tracefs '%s' entry\n", name);
return ret;
}
@@ -6034,9 +6267,9 @@ static struct dentry *trace_options_init_dentry(struct trace_array *tr)
if (IS_ERR(d_tracer))
return NULL;
- tr->options = debugfs_create_dir("options", d_tracer);
+ tr->options = tracefs_create_dir("options", d_tracer);
if (!tr->options) {
- pr_warning("Could not create debugfs directory 'options'\n");
+ pr_warning("Could not create tracefs directory 'options'\n");
return NULL;
}
@@ -6105,7 +6338,7 @@ destroy_trace_option_files(struct trace_option_dentry *topts)
return;
for (cnt = 0; topts[cnt].opt; cnt++)
- debugfs_remove(topts[cnt].entry);
+ tracefs_remove(topts[cnt].entry);
kfree(topts);
}
@@ -6194,7 +6427,7 @@ static const struct file_operations rb_simple_fops = {
struct dentry *trace_instance_dir;
static void
-init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer);
+init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer);
static int
allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size)
@@ -6271,7 +6504,7 @@ static void free_trace_buffers(struct trace_array *tr)
#endif
}
-static int new_instance_create(const char *name)
+static int instance_mkdir(const char *name)
{
struct trace_array *tr;
int ret;
@@ -6310,17 +6543,17 @@ static int new_instance_create(const char *name)
if (allocate_trace_buffers(tr, trace_buf_size) < 0)
goto out_free_tr;
- tr->dir = debugfs_create_dir(name, trace_instance_dir);
+ tr->dir = tracefs_create_dir(name, trace_instance_dir);
if (!tr->dir)
goto out_free_tr;
ret = event_trace_add_tracer(tr->dir, tr);
if (ret) {
- debugfs_remove_recursive(tr->dir);
+ tracefs_remove_recursive(tr->dir);
goto out_free_tr;
}
- init_tracer_debugfs(tr, tr->dir);
+ init_tracer_tracefs(tr, tr->dir);
list_add(&tr->list, &ftrace_trace_arrays);
@@ -6341,7 +6574,7 @@ static int new_instance_create(const char *name)
}
-static int instance_delete(const char *name)
+static int instance_rmdir(const char *name)
{
struct trace_array *tr;
int found = 0;
@@ -6382,82 +6615,17 @@ static int instance_delete(const char *name)
return ret;
}
-static int instance_mkdir (struct inode *inode, struct dentry *dentry, umode_t mode)
-{
- struct dentry *parent;
- int ret;
-
- /* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- if (WARN_ON_ONCE(parent != trace_instance_dir))
- return -ENOENT;
-
- /*
- * The inode mutex is locked, but debugfs_create_dir() will also
- * take the mutex. As the instances directory can not be destroyed
- * or changed in any other way, it is safe to unlock it, and
- * let the dentry try. If two users try to make the same dir at
- * the same time, then the new_instance_create() will determine the
- * winner.
- */
- mutex_unlock(&inode->i_mutex);
-
- ret = new_instance_create(dentry->d_iname);
-
- mutex_lock(&inode->i_mutex);
-
- return ret;
-}
-
-static int instance_rmdir(struct inode *inode, struct dentry *dentry)
-{
- struct dentry *parent;
- int ret;
-
- /* Paranoid: Make sure the parent is the "instances" directory */
- parent = hlist_entry(inode->i_dentry.first, struct dentry, d_u.d_alias);
- if (WARN_ON_ONCE(parent != trace_instance_dir))
- return -ENOENT;
-
- /* The caller did a dget() on dentry */
- mutex_unlock(&d_inode(dentry)->i_mutex);
-
- /*
- * The inode mutex is locked, but debugfs_create_dir() will also
- * take the mutex. As the instances directory can not be destroyed
- * or changed in any other way, it is safe to unlock it, and
- * let the dentry try. If two users try to make the same dir at
- * the same time, then the instance_delete() will determine the
- * winner.
- */
- mutex_unlock(&inode->i_mutex);
-
- ret = instance_delete(dentry->d_iname);
-
- mutex_lock_nested(&inode->i_mutex, I_MUTEX_PARENT);
- mutex_lock(&d_inode(dentry)->i_mutex);
-
- return ret;
-}
-
-static const struct inode_operations instance_dir_inode_operations = {
- .lookup = simple_lookup,
- .mkdir = instance_mkdir,
- .rmdir = instance_rmdir,
-};
-
static __init void create_trace_instances(struct dentry *d_tracer)
{
- trace_instance_dir = debugfs_create_dir("instances", d_tracer);
+ trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer,
+ instance_mkdir,
+ instance_rmdir);
if (WARN_ON(!trace_instance_dir))
return;
-
- /* Hijack the dir inode operations, to allow mkdir */
- d_inode(trace_instance_dir)->i_op = &instance_dir_inode_operations;
}
static void
-init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
+init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer)
{
int cpu;
@@ -6511,10 +6679,32 @@ init_tracer_debugfs(struct trace_array *tr, struct dentry *d_tracer)
#endif
for_each_tracing_cpu(cpu)
- tracing_init_debugfs_percpu(tr, cpu);
+ tracing_init_tracefs_percpu(tr, cpu);
}
+static struct vfsmount *trace_automount(void *ingore)
+{
+ struct vfsmount *mnt;
+ struct file_system_type *type;
+
+ /*
+ * To maintain backward compatibility for tools that mount
+ * debugfs to get to the tracing facility, tracefs is automatically
+ * mounted to the debugfs/tracing directory.
+ */
+ type = get_fs_type("tracefs");
+ if (!type)
+ return NULL;
+ mnt = vfs_kern_mount(type, 0, "tracefs", NULL);
+ put_filesystem(type);
+ if (IS_ERR(mnt))
+ return NULL;
+ mntget(mnt);
+
+ return mnt;
+}
+
/**
* tracing_init_dentry - initialize top level trace array
*
@@ -6526,23 +6716,112 @@ struct dentry *tracing_init_dentry(void)
{
struct trace_array *tr = &global_trace;
+ /* The top level trace array uses NULL as parent */
if (tr->dir)
- return tr->dir;
+ return NULL;
if (WARN_ON(!debugfs_initialized()))
return ERR_PTR(-ENODEV);
- tr->dir = debugfs_create_dir("tracing", NULL);
-
+ /*
+ * As there may still be users that expect the tracing
+ * files to exist in debugfs/tracing, we must automount
+ * the tracefs file system there, so older tools still
+ * work with the newer kerenl.
+ */
+ tr->dir = debugfs_create_automount("tracing", NULL,
+ trace_automount, NULL);
if (!tr->dir) {
pr_warn_once("Could not create debugfs directory 'tracing'\n");
return ERR_PTR(-ENOMEM);
}
- return tr->dir;
+ return NULL;
+}
+
+extern struct trace_enum_map *__start_ftrace_enum_maps[];
+extern struct trace_enum_map *__stop_ftrace_enum_maps[];
+
+static void __init trace_enum_init(void)
+{
+ int len;
+
+ len = __stop_ftrace_enum_maps - __start_ftrace_enum_maps;
+ trace_insert_enum_map(NULL, __start_ftrace_enum_maps, len);
+}
+
+#ifdef CONFIG_MODULES
+static void trace_module_add_enums(struct module *mod)
+{
+ if (!mod->num_trace_enums)
+ return;
+
+ /*
+ * Modules with bad taint do not have events created, do
+ * not bother with enums either.
+ */
+ if (trace_module_has_bad_taint(mod))
+ return;
+
+ trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums);
}
-static __init int tracer_init_debugfs(void)
+#ifdef CONFIG_TRACE_ENUM_MAP_FILE
+static void trace_module_remove_enums(struct module *mod)
+{
+ union trace_enum_map_item *map;
+ union trace_enum_map_item **last = &trace_enum_maps;
+
+ if (!mod->num_trace_enums)
+ return;
+
+ mutex_lock(&trace_enum_mutex);
+
+ map = trace_enum_maps;
+
+ while (map) {
+ if (map->head.mod == mod)
+ break;
+ map = trace_enum_jmp_to_tail(map);
+ last = &map->tail.next;
+ map = map->tail.next;
+ }
+ if (!map)
+ goto out;
+
+ *last = trace_enum_jmp_to_tail(map)->tail.next;
+ kfree(map);
+ out:
+ mutex_unlock(&trace_enum_mutex);
+}
+#else
+static inline void trace_module_remove_enums(struct module *mod) { }
+#endif /* CONFIG_TRACE_ENUM_MAP_FILE */
+
+static int trace_module_notify(struct notifier_block *self,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ trace_module_add_enums(mod);
+ break;
+ case MODULE_STATE_GOING:
+ trace_module_remove_enums(mod);
+ break;
+ }
+
+ return 0;
+}
+
+static struct notifier_block trace_module_nb = {
+ .notifier_call = trace_module_notify,
+ .priority = 0,
+};
+#endif /* CONFIG_MODULES */
+
+static __init int tracer_init_tracefs(void)
{
struct dentry *d_tracer;
@@ -6552,7 +6831,7 @@ static __init int tracer_init_debugfs(void)
if (IS_ERR(d_tracer))
return 0;
- init_tracer_debugfs(&global_trace, d_tracer);
+ init_tracer_tracefs(&global_trace, d_tracer);
trace_create_file("tracing_thresh", 0644, d_tracer,
&global_trace, &tracing_thresh_fops);
@@ -6566,6 +6845,14 @@ static __init int tracer_init_debugfs(void)
trace_create_file("saved_cmdlines_size", 0644, d_tracer,
NULL, &tracing_saved_cmdlines_size_fops);
+ trace_enum_init();
+
+ trace_create_enum_file(d_tracer);
+
+#ifdef CONFIG_MODULES
+ register_module_notifier(&trace_module_nb);
+#endif
+
#ifdef CONFIG_DYNAMIC_FTRACE
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -6575,6 +6862,10 @@ static __init int tracer_init_debugfs(void)
create_trace_options_dir(&global_trace);
+ /* If the tracer was started via cmdline, create options for it here */
+ if (global_trace.current_trace != &nop_trace)
+ update_tracer_options(&global_trace, global_trace.current_trace);
+
return 0;
}
@@ -6888,7 +7179,7 @@ void __init trace_init(void)
tracepoint_printk = 0;
}
tracer_alloc_buffers();
- trace_event_init();
+ trace_event_init();
}
__init static int clear_boot_tracer(void)
@@ -6910,5 +7201,5 @@ __init static int clear_boot_tracer(void)
return 0;
}
-fs_initcall(tracer_init_debugfs);
+fs_initcall(tracer_init_tracefs);
late_initcall(clear_boot_tracer);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index dd8205a35760..d2612016de94 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -334,7 +334,7 @@ struct tracer_flags {
/**
- * struct tracer - a specific tracer and its callbacks to interact with debugfs
+ * struct tracer - a specific tracer and its callbacks to interact with tracefs
* @name: the name chosen to select it on the available_tracers file
* @init: called when one switches to this tracer (echo name > current_tracer)
* @reset: called when one switches to another tracer
@@ -1309,8 +1309,10 @@ static inline void init_ftrace_syscalls(void) { }
#ifdef CONFIG_EVENT_TRACING
void trace_event_init(void);
+void trace_event_enum_update(struct trace_enum_map **map, int len);
#else
static inline void __init trace_event_init(void) { }
+static inlin void trace_event_enum_update(struct trace_enum_map **map, int len) { }
#endif
extern struct trace_iterator *tracepoint_print_iter;
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e2d027ac66a2..ee7b94a4810a 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -223,7 +223,7 @@ FTRACE_ENTRY(bprint, bprint_entry,
__dynamic_array( u32, buf )
),
- F_printk("%pf: %s",
+ F_printk("%ps: %s",
(void *)__entry->ip, __entry->fmt),
FILTER_OTHER
@@ -238,7 +238,7 @@ FTRACE_ENTRY(print, print_entry,
__dynamic_array( char, buf )
),
- F_printk("%pf: %s",
+ F_printk("%ps: %s",
(void *)__entry->ip, __entry->buf),
FILTER_OTHER
@@ -253,7 +253,7 @@ FTRACE_ENTRY(bputs, bputs_entry,
__field( const char *, str )
),
- F_printk("%pf: %s",
+ F_printk("%ps: %s",
(void *)__entry->ip, __entry->str),
FILTER_OTHER
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e19e7578a0d3..c4de47fc5cca 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -13,7 +13,7 @@
#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
@@ -480,7 +480,7 @@ static void remove_subsystem(struct ftrace_subsystem_dir *dir)
return;
if (!--dir->nr_events) {
- debugfs_remove_recursive(dir->entry);
+ tracefs_remove_recursive(dir->entry);
list_del(&dir->list);
__put_system_dir(dir);
}
@@ -499,7 +499,7 @@ static void remove_event_file_dir(struct ftrace_event_file *file)
}
spin_unlock(&dir->d_lock);
- debugfs_remove_recursive(dir);
+ tracefs_remove_recursive(dir);
}
list_del(&file->list);
@@ -565,6 +565,7 @@ static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
char *event = NULL, *sub = NULL, *match;
+ int ret;
/*
* The buf format can be <subsystem>:<event-name>
@@ -590,7 +591,13 @@ static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
event = NULL;
}
- return __ftrace_set_clr_event(tr, match, sub, event, set);
+ ret = __ftrace_set_clr_event(tr, match, sub, event, set);
+
+ /* Put back the colon to allow this to be called again */
+ if (buf)
+ *(buf - 1) = ':';
+
+ return ret;
}
/**
@@ -1526,7 +1533,7 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
} else
__get_system(system);
- dir->entry = debugfs_create_dir(name, parent);
+ dir->entry = tracefs_create_dir(name, parent);
if (!dir->entry) {
pr_warn("Failed to create system directory %s\n", name);
__put_system(system);
@@ -1539,12 +1546,12 @@ event_subsystem_dir(struct trace_array *tr, const char *name,
dir->subsystem = system;
file->system = dir;
- entry = debugfs_create_file("filter", 0644, dir->entry, dir,
+ entry = tracefs_create_file("filter", 0644, dir->entry, dir,
&ftrace_subsystem_filter_fops);
if (!entry) {
kfree(system->filter);
system->filter = NULL;
- pr_warn("Could not create debugfs '%s/filter' entry\n", name);
+ pr_warn("Could not create tracefs '%s/filter' entry\n", name);
}
trace_create_file("enable", 0644, dir->entry, dir,
@@ -1585,9 +1592,9 @@ event_create_dir(struct dentry *parent, struct ftrace_event_file *file)
d_events = parent;
name = ftrace_event_name(call);
- file->dir = debugfs_create_dir(name, d_events);
+ file->dir = tracefs_create_dir(name, d_events);
if (!file->dir) {
- pr_warn("Could not create debugfs '%s' directory\n", name);
+ pr_warn("Could not create tracefs '%s' directory\n", name);
return -1;
}
@@ -1704,6 +1711,131 @@ __register_event(struct ftrace_event_call *call, struct module *mod)
return 0;
}
+static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
+{
+ int rlen;
+ int elen;
+
+ /* Find the length of the enum value as a string */
+ elen = snprintf(ptr, 0, "%ld", map->enum_value);
+ /* Make sure there's enough room to replace the string with the value */
+ if (len < elen)
+ return NULL;
+
+ snprintf(ptr, elen + 1, "%ld", map->enum_value);
+
+ /* Get the rest of the string of ptr */
+ rlen = strlen(ptr + len);
+ memmove(ptr + elen, ptr + len, rlen);
+ /* Make sure we end the new string */
+ ptr[elen + rlen] = 0;
+
+ return ptr + elen;
+}
+
+static void update_event_printk(struct ftrace_event_call *call,
+ struct trace_enum_map *map)
+{
+ char *ptr;
+ int quote = 0;
+ int len = strlen(map->enum_string);
+
+ for (ptr = call->print_fmt; *ptr; ptr++) {
+ if (*ptr == '\\') {
+ ptr++;
+ /* paranoid */
+ if (!*ptr)
+ break;
+ continue;
+ }
+ if (*ptr == '"') {
+ quote ^= 1;
+ continue;
+ }
+ if (quote)
+ continue;
+ if (isdigit(*ptr)) {
+ /* skip numbers */
+ do {
+ ptr++;
+ /* Check for alpha chars like ULL */
+ } while (isalnum(*ptr));
+ if (!*ptr)
+ break;
+ /*
+ * A number must have some kind of delimiter after
+ * it, and we can ignore that too.
+ */
+ continue;
+ }
+ if (isalpha(*ptr) || *ptr == '_') {
+ if (strncmp(map->enum_string, ptr, len) == 0 &&
+ !isalnum(ptr[len]) && ptr[len] != '_') {
+ ptr = enum_replace(ptr, map, len);
+ /* Hmm, enum string smaller than value */
+ if (WARN_ON_ONCE(!ptr))
+ return;
+ /*
+ * No need to decrement here, as enum_replace()
+ * returns the pointer to the character passed
+ * the enum, and two enums can not be placed
+ * back to back without something in between.
+ * We can skip that something in between.
+ */
+ continue;
+ }
+ skip_more:
+ do {
+ ptr++;
+ } while (isalnum(*ptr) || *ptr == '_');
+ if (!*ptr)
+ break;
+ /*
+ * If what comes after this variable is a '.' or
+ * '->' then we can continue to ignore that string.
+ */
+ if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) {
+ ptr += *ptr == '.' ? 1 : 2;
+ if (!*ptr)
+ break;
+ goto skip_more;
+ }
+ /*
+ * Once again, we can skip the delimiter that came
+ * after the string.
+ */
+ continue;
+ }
+ }
+}
+
+void trace_event_enum_update(struct trace_enum_map **map, int len)
+{
+ struct ftrace_event_call *call, *p;
+ const char *last_system = NULL;
+ int last_i;
+ int i;
+
+ down_write(&trace_event_sem);
+ list_for_each_entry_safe(call, p, &ftrace_events, list) {
+ /* events are usually grouped together with systems */
+ if (!last_system || call->class->system != last_system) {
+ last_i = 0;
+ last_system = call->class->system;
+ }
+
+ for (i = last_i; i < len; i++) {
+ if (call->class->system == map[i]->system) {
+ /* Save the first system if need be */
+ if (!last_i)
+ last_i = i;
+ update_event_printk(call, map[i]);
+ }
+ }
+ }
+ up_write(&trace_event_sem);
+}
+
static struct ftrace_event_file *
trace_create_new_event(struct ftrace_event_call *call,
struct trace_array *tr)
@@ -1915,7 +2047,7 @@ static int trace_module_notify(struct notifier_block *self,
static struct notifier_block trace_module_nb = {
.notifier_call = trace_module_notify,
- .priority = 0,
+ .priority = 1, /* higher than trace.c module notify */
};
#endif /* CONFIG_MODULES */
@@ -2228,7 +2360,7 @@ static inline int register_event_cmds(void) { return 0; }
/*
* The top level array has already had its ftrace_event_file
* descriptors created in order to allow for early events to
- * be recorded. This function is called after the debugfs has been
+ * be recorded. This function is called after the tracefs has been
* initialized, and we now have to create the files associated
* to the events.
*/
@@ -2311,16 +2443,16 @@ create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
struct dentry *d_events;
struct dentry *entry;
- entry = debugfs_create_file("set_event", 0644, parent,
+ entry = tracefs_create_file("set_event", 0644, parent,
tr, &ftrace_set_event_fops);
if (!entry) {
- pr_warn("Could not create debugfs 'set_event' entry\n");
+ pr_warn("Could not create tracefs 'set_event' entry\n");
return -ENOMEM;
}
- d_events = debugfs_create_dir("events", parent);
+ d_events = tracefs_create_dir("events", parent);
if (!d_events) {
- pr_warn("Could not create debugfs 'events' directory\n");
+ pr_warn("Could not create tracefs 'events' directory\n");
return -ENOMEM;
}
@@ -2412,7 +2544,7 @@ int event_trace_del_tracer(struct trace_array *tr)
down_write(&trace_event_sem);
__trace_remove_event_dirs(tr);
- debugfs_remove_recursive(tr->event_dir);
+ tracefs_remove_recursive(tr->event_dir);
up_write(&trace_event_sem);
tr->event_dir = NULL;
@@ -2534,10 +2666,10 @@ static __init int event_trace_init(void)
if (IS_ERR(d_tracer))
return 0;
- entry = debugfs_create_file("available_events", 0444, d_tracer,
+ entry = tracefs_create_file("available_events", 0444, d_tracer,
tr, &ftrace_avail_fops);
if (!entry)
- pr_warn("Could not create debugfs 'available_events' entry\n");
+ pr_warn("Could not create tracefs 'available_events' entry\n");
if (trace_define_common_fields())
pr_warn("tracing: Failed to allocate common fields");
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 12e2b99be862..174a6a71146c 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -177,7 +177,7 @@ struct ftrace_event_call __used event_##call = { \
}, \
.event.type = etype, \
.print_fmt = print, \
- .flags = TRACE_EVENT_FL_IGNORE_ENABLE | TRACE_EVENT_FL_USE_CALL_FILTER, \
+ .flags = TRACE_EVENT_FL_IGNORE_ENABLE, \
}; \
struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 2d25ad1526bb..a51e79688455 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -6,7 +6,6 @@
* is Copyright (c) Steven Rostedt <srostedt@redhat.com>
*
*/
-#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
@@ -151,7 +150,7 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth,
* The curr_ret_stack is initialized to -1 and get increased
* in this function. So it can be less than -1 only if it was
* filtered out via ftrace_graph_notrace_addr() which can be
- * set from set_graph_notrace file in debugfs by user.
+ * set from set_graph_notrace file in tracefs by user.
*/
if (current->curr_ret_stack < -1)
return -EBUSY;
@@ -1309,15 +1308,19 @@ void graph_trace_open(struct trace_iterator *iter)
{
/* pid and depth on the last trace processed */
struct fgraph_data *data;
+ gfp_t gfpflags;
int cpu;
iter->private = NULL;
- data = kzalloc(sizeof(*data), GFP_KERNEL);
+ /* We can be called in atomic context via ftrace_dump() */
+ gfpflags = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL;
+
+ data = kzalloc(sizeof(*data), gfpflags);
if (!data)
goto out_err;
- data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+ data->cpu_data = alloc_percpu_gfp(struct fgraph_cpu_data, gfpflags);
if (!data->cpu_data)
goto out_err_free;
@@ -1432,7 +1435,7 @@ static const struct file_operations graph_depth_fops = {
.llseek = generic_file_llseek,
};
-static __init int init_graph_debugfs(void)
+static __init int init_graph_tracefs(void)
{
struct dentry *d_tracer;
@@ -1445,7 +1448,7 @@ static __init int init_graph_debugfs(void)
return 0;
}
-fs_initcall(init_graph_debugfs);
+fs_initcall(init_graph_tracefs);
static __init int init_graph_trace(void)
{
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index d73f565b4e06..d0ce590f06e1 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -250,7 +250,7 @@ DEFINE_FETCH_symbol(string_size)
#define fetch_file_offset_string_size NULL
/* Fetch type information table */
-const struct fetch_type kprobes_fetch_type_table[] = {
+static const struct fetch_type kprobes_fetch_type_table[] = {
/* Special types */
[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
sizeof(u32), 1, "__data_loc char[]"),
@@ -760,7 +760,8 @@ static int create_trace_kprobe(int argc, char **argv)
/* Parse fetch argument */
ret = traceprobe_parse_probe_arg(arg, &tk->tp.size, parg,
- is_return, true);
+ is_return, true,
+ kprobes_fetch_type_table);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -1134,11 +1135,15 @@ static void
kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
{
struct ftrace_event_call *call = &tk->tp.call;
+ struct bpf_prog *prog = call->prog;
struct kprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
+ if (prog && !trace_call_bpf(prog, regs))
+ return;
+
head = this_cpu_ptr(call->perf_events);
if (hlist_empty(head))
return;
@@ -1165,11 +1170,15 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
struct pt_regs *regs)
{
struct ftrace_event_call *call = &tk->tp.call;
+ struct bpf_prog *prog = call->prog;
struct kretprobe_trace_entry_head *entry;
struct hlist_head *head;
int size, __size, dsize;
int rctx;
+ if (prog && !trace_call_bpf(prog, regs))
+ return;
+
head = this_cpu_ptr(call->perf_events);
if (hlist_empty(head))
return;
@@ -1286,7 +1295,7 @@ static int register_kprobe_event(struct trace_kprobe *tk)
kfree(call->print_fmt);
return -ENODEV;
}
- call->flags = 0;
+ call->flags = TRACE_EVENT_FL_KPROBE;
call->class->reg = kprobe_register;
call->data = tk;
ret = trace_add_event_call(call);
@@ -1310,7 +1319,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk)
return ret;
}
-/* Make a debugfs interface for controlling probe points */
+/* Make a tracefs interface for controlling probe points */
static __init int init_kprobe_trace(void)
{
struct dentry *d_tracer;
@@ -1323,20 +1332,20 @@ static __init int init_kprobe_trace(void)
if (IS_ERR(d_tracer))
return 0;
- entry = debugfs_create_file("kprobe_events", 0644, d_tracer,
+ entry = tracefs_create_file("kprobe_events", 0644, d_tracer,
NULL, &kprobe_events_ops);
/* Event list interface */
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'kprobe_events' entry\n");
/* Profile interface */
- entry = debugfs_create_file("kprobe_profile", 0444, d_tracer,
+ entry = tracefs_create_file("kprobe_profile", 0444, d_tracer,
NULL, &kprobe_profile_ops);
if (!entry)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'kprobe_profile' entry\n");
return 0;
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index b983b2fd2ca1..1769a81da8a7 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -356,17 +356,14 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
/* Recursive argument parser */
static int parse_probe_arg(char *arg, const struct fetch_type *t,
- struct fetch_param *f, bool is_return, bool is_kprobe)
+ struct fetch_param *f, bool is_return, bool is_kprobe,
+ const struct fetch_type *ftbl)
{
- const struct fetch_type *ftbl;
unsigned long param;
long offset;
char *tmp;
int ret = 0;
- ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
- BUG_ON(ftbl == NULL);
-
switch (arg[0]) {
case '$':
ret = parse_probe_vars(arg + 1, t, f, is_return, is_kprobe);
@@ -447,7 +444,7 @@ static int parse_probe_arg(char *arg, const struct fetch_type *t,
dprm->fetch_size = get_fetch_size_function(t,
dprm->fetch, ftbl);
ret = parse_probe_arg(arg, t2, &dprm->orig, is_return,
- is_kprobe);
+ is_kprobe, ftbl);
if (ret)
kfree(dprm);
else {
@@ -505,15 +502,12 @@ static int __parse_bitfield_probe_arg(const char *bf,
/* String length checking wrapper */
int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
- struct probe_arg *parg, bool is_return, bool is_kprobe)
+ struct probe_arg *parg, bool is_return, bool is_kprobe,
+ const struct fetch_type *ftbl)
{
- const struct fetch_type *ftbl;
const char *t;
int ret;
- ftbl = is_kprobe ? kprobes_fetch_type_table : uprobes_fetch_type_table;
- BUG_ON(ftbl == NULL);
-
if (strlen(arg) > MAX_ARGSTR_LEN) {
pr_info("Argument is too long.: %s\n", arg);
return -ENOSPC;
@@ -535,7 +529,8 @@ int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
}
parg->offset = *size;
*size += parg->type->size;
- ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return, is_kprobe);
+ ret = parse_probe_arg(arg, parg->type, &parg->fetch, is_return,
+ is_kprobe, ftbl);
if (ret >= 0 && t != NULL)
ret = __parse_bitfield_probe_arg(t, parg->type, &parg->fetch);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 4f815fbce16d..ab283e146b70 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -25,7 +25,7 @@
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/smp.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/ctype.h>
@@ -229,13 +229,6 @@ ASSIGN_FETCH_FUNC(file_offset, ftype), \
#define FETCH_TYPE_STRING 0
#define FETCH_TYPE_STRSIZE 1
-/*
- * Fetch type information table.
- * It's declared as a weak symbol due to conditional compilation.
- */
-extern __weak const struct fetch_type kprobes_fetch_type_table[];
-extern __weak const struct fetch_type uprobes_fetch_type_table[];
-
#ifdef CONFIG_KPROBE_EVENT
struct symbol_cache;
unsigned long update_symbol_cache(struct symbol_cache *sc);
@@ -333,7 +326,8 @@ find_event_file_link(struct trace_probe *tp, struct ftrace_event_file *file)
}
extern int traceprobe_parse_probe_arg(char *arg, ssize_t *size,
- struct probe_arg *parg, bool is_return, bool is_kprobe);
+ struct probe_arg *parg, bool is_return, bool is_kprobe,
+ const struct fetch_type *ftbl);
extern int traceprobe_conflict_field_name(const char *name,
struct probe_arg *args, int narg);
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index c3e4fcfddd45..3f34496244e9 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -327,11 +327,11 @@ static void t_stop(struct seq_file *m, void *p)
local_irq_enable();
}
-static int trace_lookup_stack(struct seq_file *m, long i)
+static void trace_lookup_stack(struct seq_file *m, long i)
{
unsigned long addr = stack_dump_trace[i];
- return seq_printf(m, "%pS\n", (void *)addr);
+ seq_printf(m, "%pS\n", (void *)addr);
}
static void print_disabled(struct seq_file *m)
diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c
index 75e19e86c954..6cf935316769 100644
--- a/kernel/trace/trace_stat.c
+++ b/kernel/trace/trace_stat.c
@@ -12,7 +12,7 @@
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
-#include <linux/debugfs.h>
+#include <linux/tracefs.h>
#include "trace_stat.h"
#include "trace.h"
@@ -65,7 +65,7 @@ static void reset_stat_session(struct stat_session *session)
static void destroy_session(struct stat_session *session)
{
- debugfs_remove(session->file);
+ tracefs_remove(session->file);
__reset_stat_session(session);
mutex_destroy(&session->stat_mutex);
kfree(session);
@@ -279,9 +279,9 @@ static int tracing_stat_init(void)
if (IS_ERR(d_tracing))
return 0;
- stat_dir = debugfs_create_dir("trace_stat", d_tracing);
+ stat_dir = tracefs_create_dir("trace_stat", d_tracing);
if (!stat_dir)
- pr_warning("Could not create debugfs "
+ pr_warning("Could not create tracefs "
"'trace_stat' entry\n");
return 0;
}
@@ -291,7 +291,7 @@ static int init_stat_file(struct stat_session *session)
if (!stat_dir && tracing_stat_init())
return -ENODEV;
- session->file = debugfs_create_file(session->ts->name, 0644,
+ session->file = tracefs_create_file(session->ts->name, 0644,
stat_dir,
session, &tracing_stat_fops);
if (!session->file)
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index cb3b37e533cd..6dd022c7b5bc 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -196,7 +196,7 @@ DEFINE_FETCH_file_offset(string)
DEFINE_FETCH_file_offset(string_size)
/* Fetch type information table */
-const struct fetch_type uprobes_fetch_type_table[] = {
+static const struct fetch_type uprobes_fetch_type_table[] = {
/* Special types */
[FETCH_TYPE_STRING] = __ASSIGN_FETCH_TYPE("string", string, string,
sizeof(u32), 1, "__data_loc char[]"),
@@ -535,7 +535,8 @@ static int create_trace_uprobe(int argc, char **argv)
/* Parse fetch argument */
ret = traceprobe_parse_probe_arg(arg, &tu->tp.size, parg,
- is_return, false);
+ is_return, false,
+ uprobes_fetch_type_table);
if (ret) {
pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
goto error;
@@ -1005,7 +1006,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
return true;
list_for_each_entry(event, &filter->perf_events, hw.tp_list) {
- if (event->hw.tp_target->mm == mm)
+ if (event->hw.target->mm == mm)
return true;
}
@@ -1015,7 +1016,7 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm)
static inline bool
uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event)
{
- return __uprobe_perf_filter(&tu->filter, event->hw.tp_target->mm);
+ return __uprobe_perf_filter(&tu->filter, event->hw.target->mm);
}
static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
@@ -1023,10 +1024,10 @@ static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event)
bool done;
write_lock(&tu->filter.rwlock);
- if (event->hw.tp_target) {
+ if (event->hw.target) {
list_del(&event->hw.tp_list);
done = tu->filter.nr_systemwide ||
- (event->hw.tp_target->flags & PF_EXITING) ||
+ (event->hw.target->flags & PF_EXITING) ||
uprobe_filter_event(tu, event);
} else {
tu->filter.nr_systemwide--;
@@ -1046,7 +1047,7 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event)
int err;
write_lock(&tu->filter.rwlock);
- if (event->hw.tp_target) {
+ if (event->hw.target) {
/*
* event->parent != NULL means copy_process(), we can avoid
* uprobe_apply(). current->mm must be probed and we can rely
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.